© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14300
    Prev
    Next
    INDEX
    Explanations

    amenities related to recreational facilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.57
    richTextPanel
    -0.51
     peggio
    -0.47
     zakon
    -0.47
    exion
    -0.47
    tecido
    -0.45
     cepillo
    -0.44
    RegistryLite
    -0.44
     Catawiki
    -0.44
     Noten
    -0.43
    POSITIVE LOGITS
     swimming
    0.94
     swim
    0.92
     Swimming
    0.88
     pool
    0.85
    Swimming
    0.84
     piscina
    0.80
     swimmers
    0.79
     zwem
    0.79
     bathing
    0.77
    swimming
    0.77
    Activations Density 0.053%

    No Known Activations